api-security-review
Pass
Audited by Gen Agent Trust Hub on Nov 3, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill processes untrusted user data via the
$ARGUMENTSplaceholder to perform its primary function of reviewing API security. - Ingestion points: The
$ARGUMENTSvariable inSKILL.mdis the primary entry point for external content (API descriptions or code) into the agent's context. - Boundary markers: The skill does not utilize specific delimiters (like triple backticks or XML tags) or safety instructions to isolate the user-provided data from the system instructions.
- Capability inventory: The skill is purely instructional; it does not invoke external scripts, tools, or shell commands, and it lacks file system or network access capabilities.
- Sanitization: No evidence of input validation, filtering, or sanitization of the content provided in
$ARGUMENTSis present.
Audit Metadata